https://docs.n8n.io/hosting/starter-kits/ai-starter-kit/
The Self-hosted AI Starter Kit is an open Docker Compose template that provides a fully equipped local AI and low-code development environment. Curated by n8n, it combines the self-hosted n8n platform with a selection of compatible AI products and components to help you get started building AI workflows that run on your own hardware.
What Is Included in the Starter Kit?
- Self-hosted n8n: A low-code platform with over 400 integrations and advanced AI components.
- Ollama: A cross-platform LLM platform for installing and running the latest local LLMs.
- Qdrant: An open-source, high-performance vector store with a comprehensive API.
- PostgreSQL: A database that securely handles large amounts of data.
Possible Use Cases
Here are a few use cases for the starter kit. There are surely thousands more.
- AI agents that can schedule appointments.
- Summaries of PDFs without sharing the data externally.
- Smarter bots (for example, in Slack or Telegram) for company communications and IT operations.
- Private, low-cost analysis of financial documents.
Getting Started
Clone the GitHub repository and start the setup with Docker Compose. There is one additional consideration for Nvidia graphics cards.
git clone https://github.com/n8n-io/self-hosted-ai-starter-kit.git cd self-hosted-ai-starter-kit docker compose up # With an Nvidia GPU docker compose --profile gpu-nvidia up
In general, I only recommend running an LLM on local hardware if you have a reasonably powerful GPU.
Note: This kit is intended for testing. It is not fully optimized for production environments, but it combines robust components that work well together for proof-of-concept projects. Adapt it to your needs and make sure you secure and harden it before using it in production.